diff --git a/docs/my-website/docs/providers/nlp_cloud.md b/docs/my-website/docs/providers/nlp_cloud.md
new file mode 100644
index 00000000000..441fc22ee41
--- /dev/null
+++ b/docs/my-website/docs/providers/nlp_cloud.md
@@ -0,0 +1,55 @@
+# NLP Cloud
+
+LiteLLM supports all LLMs on NLP Cloud.
+
+## quick start
+
+```python
+import os
+from litellm import completion 
+
+# set env 
+os.environ["NLP_CLOUD_API_KEY"] = "your-key"
+
+messages = [{"role": "user", "content": "Hey! how's it going?"}]
+response = completion(model="dolphin", messages=messages)
+print(response)
+```
+
+## streaming 
+Just set `stream=True` when calling completion.
+
+```python
+import os
+from litellm import completion 
+
+# set env 
+os.environ["NLP_CLOUD_API_KEY"] = "your-key"
+
+messages = [{"role": "user", "content": "Hey! how's it going?"}]
+response = completion(model="dolphin", messages=messages, stream=True)
+for chunk in response:
+    print(chunk["choices"][0]["delta"]["content"])  # same as openai format
+```
+
+## non-dolphin models 
+
+By default, LiteLLM will map `dolphin` and `chatdolphin` to nlp cloud. 
+
+If you're trying to call any other model (e.g. GPT-J, Llama-2, etc.) with nlp cloud, just set it as your custom llm provider. 
+
+
+```python
+import os
+from litellm import completion 
+
+# set env 
+os.environ["NLP_CLOUD_API_KEY"] = "your-key"
+
+messages = [{"role": "user", "content": "Hey! how's it going?"}]
+
+# e.g. to call Llama2 on NLP Cloud
+response = completion(model="nlp_cloud/finetuned-llama-2-70b", messages=messages, stream=True)
+for chunk in response:
+    print(chunk["choices"][0]["delta"]["content"])  # same as openai format
+```
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
index 18470bee885..abc790f92b0 100644
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -61,6 +61,7 @@ const sidebars = {
         "providers/huggingface", 
         "providers/vllm", 
         "providers/ai21", 
+        "providers/nlp_cloud",
         "providers/replicate", 
         "providers/cohere", 
         "providers/togetherai",